eliept1's picture
First Push
9e8bb0a
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0603442192077637,
"min": 1.0519845485687256,
"max": 2.8557047843933105,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10147.494140625,
"min": 10147.494140625,
"max": 29433.75,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.966724395751953,
"min": 0.09210042655467987,
"max": 12.966724395751953,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.51123046875,
"min": 17.867483139038086,
"max": 2643.7958984375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07302687807432627,
"min": 0.06234731367258778,
"max": 0.07665080499844443,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2921075122973051,
"min": 0.24938925469035111,
"max": 0.3832540249922221,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2077783463048,
"min": 0.08655472721119284,
"max": 0.29966379491721884,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8311133852192,
"min": 0.34621890884477136,
"max": 1.498318974586094,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 24.931818181818183,
"min": 2.75,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 121.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 2.75,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 121.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1693389366",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1693389920"
},
"total": 554.0766438339999,
"count": 1,
"self": 0.4848014560000138,
"children": {
"run_training.setup": {
"total": 0.08791001199995208,
"count": 1,
"self": 0.08791001199995208
},
"TrainerController.start_learning": {
"total": 553.503932366,
"count": 1,
"self": 0.7735580129885875,
"children": {
"TrainerController._reset_env": {
"total": 1.6098068259999536,
"count": 1,
"self": 1.6098068259999536
},
"TrainerController.advance": {
"total": 550.9696886270115,
"count": 18205,
"self": 0.3737694680137338,
"children": {
"env_step": {
"total": 550.5959191589977,
"count": 18205,
"self": 449.1883426850176,
"children": {
"SubprocessEnvManager._take_step": {
"total": 101.03269846099727,
"count": 18205,
"self": 2.093043982995482,
"children": {
"TorchPolicy.evaluate": {
"total": 98.93965447800178,
"count": 18205,
"self": 98.93965447800178
}
}
},
"workers": {
"total": 0.37487801298289014,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 551.6513326540045,
"count": 18205,
"is_parallel": true,
"self": 243.08316954601673,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0073187940000707385,
"count": 1,
"is_parallel": true,
"self": 0.005029554000202552,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022892399998681867,
"count": 10,
"is_parallel": true,
"self": 0.0022892399998681867
}
}
},
"UnityEnvironment.step": {
"total": 0.04858947899992927,
"count": 1,
"is_parallel": true,
"self": 0.0008444029999736813,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047959899995930755,
"count": 1,
"is_parallel": true,
"self": 0.00047959899995930755
},
"communicator.exchange": {
"total": 0.04445580699996299,
"count": 1,
"is_parallel": true,
"self": 0.04445580699996299
},
"steps_from_proto": {
"total": 0.002809670000033293,
"count": 1,
"is_parallel": true,
"self": 0.0005462660001285258,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022634039999047673,
"count": 10,
"is_parallel": true,
"self": 0.0022634039999047673
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 308.56816310798774,
"count": 18204,
"is_parallel": true,
"self": 12.796027883987449,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.025597744000493,
"count": 18204,
"is_parallel": true,
"self": 7.025597744000493
},
"communicator.exchange": {
"total": 242.87700455500908,
"count": 18204,
"is_parallel": true,
"self": 242.87700455500908
},
"steps_from_proto": {
"total": 45.86953292499072,
"count": 18204,
"is_parallel": true,
"self": 8.862219116044685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.00731380894604,
"count": 182040,
"is_parallel": true,
"self": 37.00731380894604
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.000129345999994257,
"count": 1,
"self": 0.000129345999994257,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 546.5301745549651,
"count": 523737,
"is_parallel": true,
"self": 12.259187916952783,
"children": {
"process_trajectory": {
"total": 291.84821047201297,
"count": 523737,
"is_parallel": true,
"self": 290.4772755250126,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3709349470003644,
"count": 4,
"is_parallel": true,
"self": 1.3709349470003644
}
}
},
"_update_policy": {
"total": 242.42277616599938,
"count": 90,
"is_parallel": true,
"self": 94.18687589200363,
"children": {
"TorchPPOOptimizer.update": {
"total": 148.23590027399575,
"count": 4584,
"is_parallel": true,
"self": 148.23590027399575
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15074955399995815,
"count": 1,
"self": 0.0010274900000695197,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14972206399988863,
"count": 1,
"self": 0.14972206399988863
}
}
}
}
}
}
}